tCLD-Net: A Transfer Learning Internet Encrypted Traffic Classification Scheme Based on Convolution Neural Network and Long Short-Term Memory Network

Hu, Xinyi; Gu, Chunxiang; Chen, Yihang; Wei, Fushan

doi:10.1109/ccci52664.2021.9583214

Cited by 6 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Two neural networks, Convolutional Neural Networks (CNN) and Long-Short Term Memory are used by researchers in [30] to classify Facebook and Hangout based applications.…”

Section: Deep Learningmentioning

confidence: 99%

Classification of Flow-based Network Applications using Fuzzy Logic

Khan,

Farooq

2023

Preprint

View full text Add to dashboard Cite

Ever since the boom of social media, the internet has drastically changed our lives. From social mediaplatforms, Industry 4.0, Big Data, Cloud Computing to Augmented and Virtual reality, the amountof data on the internet has increased on an unprecedented scale, and it is not going to decrease in theyears to come. This increasing amount of data puts a huge strain on today’s network infrastructure. Itis the need of the hour to keep the internet infrastructure up-to-date to tackle the upcoming challenges.Internet Network Traffic Classification is thus a new paradigm in which lightweight sophisticatedalgorithms are designed and tested on live networks. This problem has been focused a lot with thehelp of Machine and Deep learning tools. These models do provide a high accuracy of result, but canbecome complex problems depending upon the specific application. In this paper, a Fuzzy Logic basedLightweight Classification Architecture is proposed and implemented to successfully identify Audioand Video from other Network Traffic (NT) applications. A detailed elaboration of features extractedfrom a variety of applications is presented. Fuzzy logic is used to distinguish among the classes basedon human intuition based rules. To verify the proposed algorithm, flow-based network captures isused to identify whether the correct class of network traffic is predicted or not. The results obtainedfrom the Fuzzy logic is also compared with traditional Logistic regression and kNN based MachineLearning algorithms to showcase the superiority of Fuzzy logic.

show abstract

“…Two neural networks, Convolutional Neural Networks (CNN) and Long-Short Term Memory are used by researchers in [30] to classify Facebook and Hangout based applications.…”

Section: Deep Learningmentioning

confidence: 99%

Classification of Flow-based Network Applications using Fuzzy Logic

Khan,

Farooq

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Among them, the function of encoder is to reduce feature dimensions and approximate the distribution of latent variable z via inferring statistical mean and variance. A decoder is responsible to generate target data according to the randomly sampled z. Reparameterization is a trick to realize sampling from distribution, as shown in equation (10).…”

Section: Mvae-reinforcementmentioning

confidence: 99%

“…e goal of the model is to obtain approximate data in the same space as original data. In order to achieve this goal, the loss function, as shown in equation (10), is composed of reconstruction loss (equation ( 11)) and KL loss (Equation (12)). e reconstruction loss, mean square error function (MSE), is to calculate the difference between the input and output.…”

Section: Mvae-reinforcementmentioning

confidence: 99%

See 1 more Smart Citation

A Network Data Reinforcement Method Based on the Multiclass Variational Autoencoder

Jiang

et al. 2022

Security and Communication Networks

View full text Add to dashboard Cite

Anomaly detection models based on deep learning come up against difficulties on the deployment in real scenarios such as generalization problem. The performance of the model based on specific dataset is not as good as expected in other scenarios. In order to avoid this problem, it is a feasible solution to collect network data from the target environment to train the model. This paper proposes a network data reinforcement method based on the multiclass variational autoencoder to complete training tasks with little amount data. In this paper, anomaly detection models based on MLP and CNN are designed, respectively, and validation experiments are carried out on the CICIDS-2018 dataset. Compared with unreinforced models, models based on this method get faster convergence speed during training. During evaluation, models based on this method achieve an average accuracy of 93.69%, while unreinforced models only get an average accuracy of 55.63%. In addition, this method provides competitive results on insufficient data compared with those existing models on sufficient data.

show abstract

Domain Adaptation with Maximum Margin Criterion with Application to Network Traffic Classification

Taghiyarrenani

Farsi

2023

Communications in Computer and Information Science

View full text Add to dashboard Cite

tCLD-Net: A Transfer Learning Internet Encrypted Traffic Classification Scheme Based on Convolution Neural Network and Long Short-Term Memory Network

Cited by 6 publications

References 10 publications

Classification of Flow-based Network Applications using Fuzzy Logic

Classification of Flow-based Network Applications using Fuzzy Logic

A Network Data Reinforcement Method Based on the Multiclass Variational Autoencoder

Domain Adaptation with Maximum Margin Criterion with Application to Network Traffic Classification

Contact Info

Product

Resources

About